Merge branch 'harden-and-extend-elf-build-id-parsing-logic'

Andrii Nakryiko says:

====================
Harden and extend ELF build ID parsing logic

The goal of this patch set is to extend existing ELF build ID parsing logic,
currently mostly used by BPF subsystem, with support for working in sleepable
mode in which memory faults are allowed and can be relied upon to fetch
relevant parts of ELF file to find and fetch .note.gnu.build-id information.

This is useful and important for BPF subsystem itself, but also for
PROCMAP_QUERY ioctl(), built atop of /proc/<pid>/maps functionality (see [0]),
which makes use of the same build_id_parse() functionality. PROCMAP_QUERY is
always called from sleepable user process context, so it doesn't have to
suffer from current restrictions of build_id_parse() which are due to the NMI
context assumption.

Along the way, we harden the logic to avoid TOCTOU, overflow, out-of-bounds
access problems.  This is the very first patch, which can be backported to
older releases, if necessary.

We also lift existing limitations of only working as long as ELF program
headers and build ID note section is contained strictly within the very first
page of ELF file.

We achieve all of the above without duplication of logic between sleepable and
non-sleepable modes through freader abstraction that manages underlying folio
from page cache (on demand) and gives a simple to use direct memory access
interface. With that, single page restrictions and adding sleepable mode
support is rather straightforward.

We also extend existing set of BPF selftests with a few tests targeting build
ID logic across sleepable and non-sleepabe contexts (we utilize sleepable and
non-sleepable uprobes for that).

   [0] https://lore.kernel.org/linux-mm/20240627170900.1672542-4-andrii@kernel.org/

v6->v7:
  - added filemap_invalidate_{lock,unlock}_shared() around read_cache_folio
    and kept Eduard's Reviewed-by (Eduard);
v5->v6:
  - use local phnum variable in get_build_id_32() (Jann);
  - switch memcmp() instead of strcmp() in parse_build_id() (Jann);
v4->v5:
  - pass proper file reference to read_cache_folio() (Shakeel);
  - fix another potential overflow due to two u32 additions (Andi);
  - add PageUptodate() check to patch #1 (Jann);
v3->v4:
  - fix few more potential overflow and out-of-bounds access issues (Andi);
  - use purely folio-based implementation for freader (Matthew);
v2->v3:
  - remove unneeded READ_ONCE()s and force phoff to u64 for 32-bit mode (Andi);
  - moved hardening fixes to the front for easier backporting (Jann);
  - call freader_cleanup() from build_id_parse_buf() for consistency (Jiri);
v1->v2:
  - ensure MADV_PAGEOUT works reliably by paging data in first (Shakeel);
  - to fix BPF CI build optionally define MADV_POPULATE_READ in selftest.
====================

Link: https://lore.kernel.org/r/20240829174232.3133883-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 105 insertions, 33 deletions

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index c99f8e5234ac..3615c06b7dfa 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -124,8 +124,24 @@ free_smap:
 	return ERR_PTR(err);
 }
 
+static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, bool may_fault)
+{
+	return may_fault ? build_id_parse(vma, build_id, NULL)
+			 : build_id_parse_nofault(vma, build_id, NULL);
+}
+
+/*
+ * Expects all id_offs[i].ip values to be set to correct initial IPs.
+ * They will be subsequently:
+ *   - either adjusted in place to a file offset, if build ID fetching
+ *     succeeds; in this case id_offs[i].build_id is set to correct build ID,
+ *     and id_offs[i].status is set to BPF_STACK_BUILD_ID_VALID;
+ *   - or IP will be kept intact, if build ID fetching failed; in this case
+ *     id_offs[i].build_id is zeroed out and id_offs[i].status is set to
+ *     BPF_STACK_BUILD_ID_IP.
+ */
 static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
-					  u64 *ips, u32 trace_nr, bool user)
+					  u32 trace_nr, bool user, bool may_fault)
 {
 	int i;
 	struct mmap_unlock_irq_work *work = NULL;
@@ -142,30 +158,28 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 		/* cannot access current->mm, fall back to ips */
 		for (i = 0; i < trace_nr; i++) {
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
-			id_offs[i].ip = ips[i];
 			memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX);
 		}
 		return;
 	}
 
 	for (i = 0; i < trace_nr; i++) {
-		if (range_in_vma(prev_vma, ips[i], ips[i])) {
+		u64 ip = READ_ONCE(id_offs[i].ip);
+
+		if (range_in_vma(prev_vma, ip, ip)) {
 			vma = prev_vma;
-			memcpy(id_offs[i].build_id, prev_build_id,
-			       BUILD_ID_SIZE_MAX);
+			memcpy(id_offs[i].build_id, prev_build_id, BUILD_ID_SIZE_MAX);
 			goto build_id_valid;
 		}
-		vma = find_vma(current->mm, ips[i]);
-		if (!vma || build_id_parse(vma, id_offs[i].build_id, NULL)) {
+		vma = find_vma(current->mm, ip);
+		if (!vma || fetch_build_id(vma, id_offs[i].build_id, may_fault)) {
 			/* per entry fall back to ips */
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
-			id_offs[i].ip = ips[i];
 			memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX);
 			continue;
 		}
 build_id_valid:
-		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i]
-			- vma->vm_start;
+		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ip - vma->vm_start;
 		id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
 		prev_vma = vma;
 		prev_build_id = id_offs[i].build_id;
@@ -216,7 +230,7 @@ static long __bpf_get_stackid(struct bpf_map *map,
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
 	struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
 	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
-	u32 hash, id, trace_nr, trace_len;
+	u32 hash, id, trace_nr, trace_len, i;
 	bool user = flags & BPF_F_USER_STACK;
 	u64 *ips;
 	bool hash_matches;
@@ -238,15 +252,18 @@ static long __bpf_get_stackid(struct bpf_map *map,
 		return id;
 
 	if (stack_map_use_build_id(map)) {
+		struct bpf_stack_build_id *id_offs;
+
 		/* for build_id+offset, pop a bucket before slow cmp */
 		new_bucket = (struct stack_map_bucket *)
 			pcpu_freelist_pop(&smap->freelist);
 		if (unlikely(!new_bucket))
 			return -ENOMEM;
 		new_bucket->nr = trace_nr;
-		stack_map_get_build_id_offset(
-			(struct bpf_stack_build_id *)new_bucket->data,
-			ips, trace_nr, user);
+		id_offs = (struct bpf_stack_build_id *)new_bucket->data;
+		for (i = 0; i < trace_nr; i++)
+			id_offs[i].ip = ips[i];
+		stack_map_get_build_id_offset(id_offs, trace_nr, user, false /* !may_fault */);
 		trace_len = trace_nr * sizeof(struct bpf_stack_build_id);
 		if (hash_matches && bucket->nr == trace_nr &&
 		    memcmp(bucket->data, new_bucket->data, trace_len) == 0) {
@@ -387,7 +404,7 @@ const struct bpf_func_proto bpf_get_stackid_proto_pe = {
 
 static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 			    struct perf_callchain_entry *trace_in,
-			    void *buf, u32 size, u64 flags)
+			    void *buf, u32 size, u64 flags, bool may_fault)
 {
 	u32 trace_nr, copy_len, elem_size, num_elem, max_depth;
 	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
@@ -405,8 +422,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	if (kernel && user_build_id)
 		goto clear;
 
-	elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id)
-					    : sizeof(u64);
+	elem_size = user_build_id ? sizeof(struct bpf_stack_build_id) : sizeof(u64);
 	if (unlikely(size % elem_size))
 		goto clear;
 
@@ -427,6 +443,9 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	if (sysctl_perf_event_max_stack < max_depth)
 		max_depth = sysctl_perf_event_max_stack;
 
+	if (may_fault)
+		rcu_read_lock(); /* need RCU for perf's callchain below */
+
 	if (trace_in)
 		trace = trace_in;
 	else if (kernel && task)
@@ -434,21 +453,34 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	else
 		trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
 					   crosstask, false);
-	if (unlikely(!trace))
-		goto err_fault;
 
-	if (trace->nr < skip)
+	if (unlikely(!trace) || trace->nr < skip) {
+		if (may_fault)
+			rcu_read_unlock();
 		goto err_fault;
+	}
 
 	trace_nr = trace->nr - skip;
 	trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem;
 	copy_len = trace_nr * elem_size;
 
 	ips = trace->ip + skip;
-	if (user && user_build_id)
-		stack_map_get_build_id_offset(buf, ips, trace_nr, user);
-	else
+	if (user_build_id) {
+		struct bpf_stack_build_id *id_offs = buf;
+		u32 i;
+
+		for (i = 0; i < trace_nr; i++)
+			id_offs[i].ip = ips[i];
+	} else {
 		memcpy(buf, ips, copy_len);
+	}
+
+	/* trace/ips should not be dereferenced after this point */
+	if (may_fault)
+		rcu_read_unlock();
+
+	if (user_build_id)
+		stack_map_get_build_id_offset(buf, trace_nr, user, may_fault);
 
 	if (size > copy_len)
 		memset(buf + copy_len, 0, size - copy_len);
@@ -464,7 +496,7 @@ clear:
 BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
 	   u64, flags)
 {
-	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
+	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, false /* !may_fault */);
 }
 
 const struct bpf_func_proto bpf_get_stack_proto = {
@@ -477,8 +509,24 @@ const struct bpf_func_proto bpf_get_stack_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
-	   u32, size, u64, flags)
+BPF_CALL_4(bpf_get_stack_sleepable, struct pt_regs *, regs, void *, buf, u32, size,
+	   u64, flags)
+{
+	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, true /* may_fault */);
+}
+
+const struct bpf_func_proto bpf_get_stack_sleepable_proto = {
+	.func		= bpf_get_stack_sleepable,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+static long __bpf_get_task_stack(struct task_struct *task, void *buf, u32 size,
+				 u64 flags, bool may_fault)
 {
 	struct pt_regs *regs;
 	long res = -EINVAL;
@@ -488,12 +536,18 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 
 	regs = task_pt_regs(task);
 	if (regs)
-		res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
+		res = __bpf_get_stack(regs, task, NULL, buf, size, flags, may_fault);
 	put_task_stack(task);
 
 	return res;
 }
 
+BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
+	   u32, size, u64, flags)
+{
+	return __bpf_get_task_stack(task, buf, size, flags, false /* !may_fault */);
+}
+
 const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.func		= bpf_get_task_stack,
 	.gpl_only	= false,
@@ -505,6 +559,23 @@ const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_get_task_stack_sleepable, struct task_struct *, task, void *, buf,
+	   u32, size, u64, flags)
+{
+	return __bpf_get_task_stack(task, buf, size, flags, true /* !may_fault */);
+}
+
+const struct bpf_func_proto bpf_get_task_stack_sleepable_proto = {
+	.func		= bpf_get_task_stack_sleepable,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 	   void *, buf, u32, size, u64, flags)
 {
@@ -516,7 +587,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 	__u64 nr_kernel;
 
 	if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN))
-		return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
+		return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, false /* !may_fault */);
 
 	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
 			       BPF_F_USER_BUILD_ID)))
@@ -536,7 +607,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 		__u64 nr = trace->nr;
 
 		trace->nr = nr_kernel;
-		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags);
+		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */);
 
 		/* restore nr */
 		trace->nr = nr;
@@ -548,7 +619,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 			goto clear;
 
 		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
-		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags);
+		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */);
 	}
 	return err;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c973e3c11e03..c78a77f9dce4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8851,7 +8851,7 @@ got_name:
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
 	if (atomic_read(&nr_build_id_events))
-		build_id_parse(vma, mmap_event->build_id, &mmap_event->build_id_size);
+		build_id_parse_nofault(vma, mmap_event->build_id, &mmap_event->build_id_size);
 
 	perf_iterate_sb(perf_event_mmap_output,
 		       mmap_event,
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 98e395f1baae..68b5905c6eb5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1507,7 +1507,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
 	case BPF_FUNC_get_task_stack:
-		return &bpf_get_task_stack_proto;
+		return prog->sleepable ? &bpf_get_task_stack_sleepable_proto
+				       : &bpf_get_task_stack_proto;
 	case BPF_FUNC_copy_from_user:
 		return &bpf_copy_from_user_proto;
 	case BPF_FUNC_copy_from_user_task:
@@ -1563,7 +1564,7 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto;
 	case BPF_FUNC_get_stack:
-		return &bpf_get_stack_proto;
+		return prog->sleepable ? &bpf_get_stack_sleepable_proto : &bpf_get_stack_proto;
 #ifdef CONFIG_BPF_KPROBE_OVERRIDE
 	case BPF_FUNC_override_return:
 		return &bpf_override_return_proto;